Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a369a7652fbe38a54ebbb78e43ce2875cdc2d4e63bba5d69d29ff113c327f05
+oid sha256:2e83963060cff4482c40910db50e7f11f5d9fa29a7ac21cc043c9c1d811f2028
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1db19691022a2ea3c2de0e91cd3a49fca490d5cc3b9d8fa9cc6e602f4a6c5e9d
+oid sha256:8f4011e63b3aab2acda238b08f0f175aaba58caaf4cdd8fd358293e6b2630153
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000506906602458497,
+  "epoch": 0.001013813204916994,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 17.279,
       "eval_steps_per_second": 8.639,
       "step": 2
+    },
+    {
+      "epoch": 0.0007603599036877456,
+      "grad_norm": 0.15520311892032623,
+      "learning_rate": 3e-05,
+      "loss": 1.1812,
+      "step": 3
+    },
+    {
+      "epoch": 0.001013813204916994,
+      "grad_norm": 0.15153363347053528,
+      "learning_rate": 4e-05,
+      "loss": 1.069,
+      "step": 4
+    },
+    {
+      "epoch": 0.001013813204916994,
+      "eval_loss": 1.113523006439209,
+      "eval_runtime": 255.6171,
+      "eval_samples_per_second": 26.0,
+      "eval_steps_per_second": 13.0,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1312077863976960.0,
+  "total_flos": 2624155727953920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null